Sciweavers

113 search results - page 5 / 23
» Improving Corpus Comparability for Bilingual Lexicon Extract...
Sort
View
ACL
2010
13 years 5 months ago
Bilingual Lexicon Generation Using Non-Aligned Signatures
Bilingual lexicons are fundamental resources. Modern automated lexicon generation methods usually require parallel corpora, which are not available for most language pairs. Lexico...
Daphna Shezaf, Ari Rappoport
EACL
2006
ACL Anthology
13 years 8 months ago
Compiling French-Japanese Terminologies from the Web
We propose a method for compiling bilingual terminologies of multi-word terms (MWTs) for given translation pairs of seed terms. Traditional methods for bilingual terminology compi...
Xavier Robitaille, Yasuhiro Sasaki, Masatsugu Tono...
EMNLP
2008
13 years 8 months ago
Syntactic Constraints on Paraphrases Extracted from Parallel Corpora
We improve the quality of paraphrases extracted from parallel corpora by requiring that phrases and their paraphrases be the same syntactic type. This is achieved by parsing the E...
Chris Callison-Burch
INLG
2010
Springer
13 years 5 months ago
Extracting Parallel Fragments from Comparable Corpora for Data-to-text Generation
Building NLG systems, in particular statistical ones, requires parallel data (paired inputs and outputs) which do not generally occur naturally. In this paper, we investigate the ...
Anja Belz, Eric Kow